AI 中文总结
研究LIGO-Virgo-KAGRA网络探测引力波事件中，不同天体物理效应信号相似性带来的问题，用卷积神经网络训练分类器区分微透镜与无透镜非自旋引力波信号，评估不同信号分类准确率及模型泛化性，提出低延迟机器学习管道。
AI 中文摘要
LIGO-Virgo-KAGRA网络已探测到近400次引力波（GW）事件，未来还有更多。不同天体物理效应产生的信号相似性会使基于模板的搜索和参数估计复杂化。自旋进动产生的GW调制可能类似于质量为10至10^5M⊙的致密天体微引力透镜引起的拍频模式。研究这种简并性并评估机器学习能否区分这些效应。生成20000个模拟GW信号，训练卷积神经网络。分类器在高斯噪声中准确率达95%，在实际探测器噪声中达82%。还研究了微透镜（ML）与无透镜非自旋（UN）信号以及无透镜非自旋与无透镜进动（UP）信号的分类。区分UN与UP即使在高斯噪声中也困难，ML与UN分类在实际噪声中准确率达80%。确定分类器最佳参数空间区域并在实际GW事件上评估，发现高斯噪声训练的模型泛化性更好。首次提出区分微透镜与无透镜非自旋GW信号的低延迟机器学习管道。
英文摘要
With nearly 400 Gravitational Wave (GW) events detected by the LIGO-Virgo-KAGRA network and many more expected, similarities between signals produced by different astrophysical effects can complicate template-based searches and parameter estimation. In particular, GW modulations from spin precession can resemble the beating pattern induced by microlensing from compact objects with masses of $10$-$10^5,M_\odot$. We investigate this degeneracy and assess whether machine learning can distinguish between these effects. We generate 20,000 simulated GW signals for each class with a network optimal signal-to-noise ratio above 20 and train a convolutional neural network on time-frequency (Q-transform) spectrograms. The classifier achieves up to 95% accuracy in Gaussian noise and 82% in real detector noise. We also study classification between microlensed (ML) and unlensed non-spinning (UN) signals, as well as between unlensed non-spinning (UN) and unlensed precessing (UP) signals. While distinguishing UN from UP remains difficult even in Gaussian noise, ML vs. UN classification reaches up to 80% accuracy in real noise. We identify the regions of parameter space where the classifier performs best and evaluate the ML-UN network on real GW events, finding that the model trained on Gaussian noise generalizes better than the one trained on real noise. This work presents the first low-latency machine-learning pipeline for distinguishing microlensed from unlensed non-spinning GW signals.
